SEARCH · Search NASA
Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.
Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.
The contents include: 1) A brief history of NPB; 2) What is (not) being measured by NPB; 3) Irregular dynamic applications (UA Benchmark); and 4) Wide area distributed computing (NAS Grid Benchmarks-NGB). This paper is presented in viewgraph form.
Problems which can arise with vector and parallel computers are discussed in a user oriented context. Emphasis is placed on the algorithms used and the programming techniques adopted. Three recently developed supercomputers are examined and typical application examples are given in CRAY FORTRAN, CYBER 205 FORTRAN and DAP (distributed array processor) FORTRAN. The systems performance is compared. The addition of parts of two N x N arrays is considered. The influence of the architecture on the algorithms and programming language is demonstrated. Numerical analysis of magnetohydrodynamic differential equations by an explicit difference method is illustrated, showing very good results for all three systems. The prognosis for supercomputer development is assessed.
Coinduction is a powerful technique for reasoning about unfounded sets, unbounded structures, infinite automata, and interactive computations [6]. Where induction corresponds to least fixed point's semantics, coinduction corresponds to greatest fixed point semantics. Recently coinduction has been incorporated into logic programming and an elegant operational semantics developed for it [11, 12]. This operational semantics is the greatest fix point counterpart of SLD resolution (SLD resolution imparts operational semantics to least fix point based computations) and is termed co- SLD resolution. In co-SLD resolution, a predicate goal p( t) succeeds if it unifies with one of its ancestor calls. In addition, rational infinite terms are allowed as arguments of predicates. Infinite terms are represented as solutions to unification equations and the occurs check is omitted during the unification process. Coinductive Logic Programming (Co-LP) and Co-SLD resolution can be used to elegantly perform model checking and planning. A combined SLD and Co-SLD resolution based LP system forms the common basis for planning, scheduling, verification, model checking, and constraint solving [9, 4]. This is achieved by amalgamating SLD resolution, co-SLD resolution, and constraint logic programming [13] in a single logic programming system. Given that parallelism in logic programs can be implicitly exploited [8], complex, compute-intensive applications (planning, scheduling, model checking, etc.) can be executed in parallel on multi-core machines. Parallel execution can result in speed-ups as well as in larger instances of the problems being solved. In the remainder we elaborate on (i) how planning can be elegantly and efficiently performed under real-time constraints, (ii) how real-time systems can be elegantly and efficiently model- checked, as well as (iii) how hybrid systems can be verified in a combined system with both co-SLD and SLD resolution. Implementations of co-SLD resolution as well as preliminary implementations of the planning and verification applications have been developed [4]. Co-LP and Model Checking: The vast majority of properties that are to be verified can be classified into safety properties and liveness properties. It is well known within model checking that safety properties can be verified by reachability analysis, i.e, if a counter-example to the property exists, it can be finitely determined by enumerating all the reachable states of the Kripke structure.
A methodology, called the force, supports the construction of programs to be executed in parallel by a force of processes. The number of processes in the force is unspecified, but potentially very large. The force idea is embodied in a set of macros which produce multiproceossor FORTRAN code and has been studied on two shared memory multiprocessors of fairly different character. The method has simplified the writing of highly parallel programs within a limited class of parallel algorithms and is being extended to cover a broader class. The individual parallel constructs which comprise the force methodology are discussed. Of central concern are their semantics, implementation on different architectures and performance implications.
A high level language for the Massively Parallel Processor (MPP) was designed. This language, called Parallel Pascal, is described in detail. A description of the language design, a description of the intermediate language, Parallel P-Code, and details for the MPP implementation are included. Formal descriptions of Parallel Pascal and Parallel P-Code are given. A compiler was developed which converts programs in Parallel Pascal into the intermediate Parallel P-Code language. The code generator to complete the compiler for the MPP is being developed independently. A Parallel Pascal to Pascal translator was also developed. The architecture design for a VLSI version of the MPP was completed with a description of fault tolerant interconnection networks. The memory arrangement aspects of the MPP are discussed and a survey of other high level languages is given.
A space spider crane for the movement, placement, and or assembly of various components on or in the vicinity of a space structure is described. As permanent space structures are utilized by the space program, a means will be required to transport cargo and perform various repair tasks. A space spider crane comprising a small central body with attached manipulators and legs fulfills this requirement. The manipulators may be equipped with constant pressure gripping end effectors or tools to accomplish various repair tasks. The legs are also equipped with constant pressure gripping end effectors to grip the space structure. Control of the space spider crane may be achieved either by computer software or a remotely situated human operator, who maintains visual contact via television cameras mounted on the space spider crane. One possible walking program consists of a parallel motion walking program whereby the small central body alternatively leans forward and backward relative to end effectors.
NPB2 (NAS (NASA Advanced Supercomputing) Parallel Benchmarks 2) is an implementation, based on Fortran and the MPI (message passing interface) message passing standard, of the original NAS Parallel Benchmark specifications. NPB2 programs are run with little or no tuning, in contrast to NPB vendor implementations, which are highly optimized for specific architectures. NPB2 results complement, rather than replace, NPB results. Because they have not been optimized by vendors, NPB2 implementations approximate the performance a typical user can expect for a portable parallel program on distributed memory parallel computers. Together these results provide an insightful comparison of the real-world performance of high-performance computers. New NPB2 features: New implementation (CG), new workstation class problem sizes, new serial sample versions, more performance statistics.
The materials science challenge of providing a suite of suitable materials to satisfy the technology to achieve fusion energy is addressed in this ORNL program. The inability of currently available materials and components to withstand the harsh fusion nuclear environment requires development of new materials, and an understanding of their response to the fusion environment. The overarching goal of the ORNL Fusion Materials program is to provide the applied materials science support and materials understanding to underpin the ongoing DOE Office of Science—Fusion Energy Sciences program, in parallel with developing the materials for fusion power systems. In this effort the program continues to be integrated both with the larger U.S. and international fusion materials communities and with the U.S. and international fusion design and technology communities. The excitement of this program comes from the priorities given to this subject in the two recent fusion reviews, by the FESAC and NAS committees. An important element of those recommendations is the support for pivoting the national R&D emphasis to the Fusion Materials and Technologies (FM&T), the long-advocated Fusion Prototypic Neutron Source, and for the Fusion Pilot Plant study that will help focus program direction and efforts. Furthermore, the surge of venture capital investment into the private fusion industry start-ups over the last few years is anticipated to help accelerate all aspects of the fusion energy development. This twelfth annual report of the ORNL (Oak Ridge National Laboratory) Fusion Reactor Materials Program summarizes the accomplishments in Fiscal Year 2023 (FY2023). The year was the first to return to full post-COVID-restriction operations, with students and international assignees no longer impacted by COVID restrictions, as in FY20-21-22. Following the pattern of planning used in this program, work for the year FY2023 focused on having the data and productivity to support a strong presence at the International Conference on Fusion Reactor Materials (ICFRM) 21, organized by Spain and occurred in October 2023. Twenty-nine ORNL-led abstracts were submitted, with all accepted. Four were invited presentations, nine contributed oral, fourteen posters, and two withdrawn due to unforeseen circumstances. Additionally, nine external abstracts with ORNL contributing authors were presented. These will be reported in the FY24 report next year.
The conventional wisdom in the scientific computing community is that the best way to solve large-scale numerically intensive scientific problems on today's parallel MIMD computers is to use Fortran or C programmed in a data-parallel style using low-level message-passing primitives. This approach inevitably leads to nonportable codes, extensive development time, and restricts parallel programming to the domain of the expert programmer. We believe that these problems are not inherent to parallel computing but are the result of the tools used. We will show that comparable performance can be achieved with little effort if better tools that present higher level abstractions are used.
The Cray T3D is the first-phase system in Cray Research Inc.'s (CRI) three-phase massively parallel processing program. In this report we describe the architecture of the T3D, as well as the CRAFT (Cray Research Adaptive Fortran) programming model, and contrast it with PVM, which is also supported on the T3D We present some performance data based on the NAS Parallel Benchmarks to illustrate both architectural and software features of the T3D.
Adequate prediction techniques for supersonic, mixing, reacting flows are of great importance in the design and performance analysis of supersonic combustion ramjet (scramjet) engines. Analytical programs for parallel injection flow fields with chemical reaction and turbulent mixing are now available for both single and multiple-jet flows. The application of these analyses to simple flow geometries is discussed, and comparisons also are made with data on the more complex case of multiple-jet, reacting flows. A review is given of Langley investigations of parallel injection flow fields. Among these are single-jet studies of nonreacting, turbulent mixing (H2 in air and H2 in N2), and of reacting turbulent mixing (H2 in air) with both single and multiple jets. Implications of the results of the studies for scramjet fuel injector design are discussed.
The demands for concurrent operation within a computer system and the representation of parallelism in programming languages have yielded a new form of program representation known as data flow (DENN 74, DENN 75, TREL 82a). A new model based on data flow principles for parallel computations and parallel computer systems is presented. Necessary conditions for liveness and deadlock freeness in data flow graphs are derived. The data flow graph is used as a model to represent asynchronous concurrent computer architectures including data flow computers.
In the development of complex spacecraft missions, project management authority is usually extended hierarchically from NASA's highest agency levels down to the implementing institution's project team level, through both the center and the program. In parallel with management authority, NASA utilizes a complementary, but independent, hierarchy of technical authority (TA) that extends from the agency level to the project, again, through both the center and the program. The chief engineers (CEs) who serve in this technical authority capacity oversee and report on the technical status and ensure sound engineering practices, controls, and management of the projects and programs. At the lowest level, implementing institutions assign project CEs to technically engage projects, lead development teams, and ensure sound technical principles, processes, and issue resolution. At the middle level, programs and centers independently use CEs to ensure the technical success of their projects and programs. At the agency level, NASA's mission directorate CEs maintain technical cognizance over every program and project in their directorate and advise directorate management on the technical, cost, schedule, and programmatic health of each. As part of this vertically-extended CE team, a program level CE manages a continually varying balance between penetration depth and breadth across his or her assigned missions. Teamwork issues and information integration become critical for management at all levels to ensure value-added use of both the synergy available between CEs at the various agency levels, and the independence of the technical authority at each organization.
GPU computing has established itself as a way to accelerate parallel codes in the high performance computing world. This work focuses on speeding up APNASA, a legacy CFD code used at NASA Glenn Research Center, while also drawing conclusions about the nature of GPU computing and the requirements to make GPGPU worthwhile on legacy codes. Rewriting and restructuring of the source code was avoided to limit the introduction of new bugs. The code was profiled and investigated for parallelization potential, then OpenACC directives were used to indicate parallel parts of the code. The use of OpenACC directives was not able to reduce the runtime of APNASA on either the NVIDIA Tesla discrete graphics card, or the AMD accelerated processing unit. Additionally, it was found that in order to justify the use of GPGPU, the amount of parallel work being done within a kernel would have to greatly exceed the work being done by any one portion of the APNASA code. It was determined that in order for an application like APNASA to be accelerated on the GPU, it should not be modular in nature, and the parallel portions of the code must contain a large portion of the code's computation time.
The program called CTRANS is described which was designed to perform radiative transfer computations in an atmosphere with horizontal inhomogeneities (clouds). Since the atmosphere-ground system was to be richly detailed, the Monte Carlo method was employed. This means that results are obtained through direct modeling of the physical process of radiative transport. The effects of atmopheric or ground albedo pattern detail are essentially built up from their impact upon the transport of individual photons. The CTRANS program actually tracks the photons backwards through the atmosphere, initiating them at a receiver and following them backwards along their path to the Sun. The pattern of incident photons generated through backwards tracking automatically reflects the importance to the receiver of each region of the sky. Further, through backwards tracking, the impact of the finite field of view of the receiver and variations in its response over the field of view can be directly simulated.
An effort has been underway for several years at NASA's Langley Research Center to extend the capability of Markov modeling techniques for reliability analysis to the designers of highly reliable avionic systems. This effort has been focused in the areas of increased model abstraction and increased computational capability. The reliability model generator (RMG), a software tool which uses as input a graphical, object-oriented block diagram of the system, is discussed. RMG uses an automated failure modes-effects analysis algorithm to produce the reliability model from the graphical description. Also considered is the ASSURE software tool, a parallel processing program which uses the ASSIST modeling language and SURE semi-Markov solution technique. An executable failure modes-effects analysis is used by ASSURE. The successful combination of the power of graphical representation, automated model generation, and parallel computation leads to the conclusion that large system architectures can now be analyzed.
An existing program is currently being adapted to perform finite element analysis by distributing substructures over a network of four Apple IIe microcomputers connected to a shared disk. In this network, one microcomputer controls the entire process while the others perform the analysis on each substructure in parallel. This substructure analysis is used in an iterative, fully stressed, structural resizing procedure. This procedure allows experimentatation with resizing in which all analyses are not completed during a single iteration. This research gives some insight on how to configure multidiscriplinary analysis and optimization procedures for decomposable engineering systems using either high performance engineering workstations or a parallel processor supercomputer. In addition, the operational experience gained facilitates the implementation of analysis programs on these new computers when they become available in an engineering environment.